torchtime.transforms¶

The torchtime.transforms module contains common time series processings and feature extractions.

Composition¶

Compose(transforms)

Composes several transforms together.

Convert a numpy time series to tensor and scale the values accordingly.

Replace NaN values in a time series by some value or its median.

Pads a time series to a given target length

Down/up samples the given time series to either the given size or by the given scale_factor.

`Normalize`	Normalize a tensor time series with mean and standard deviation.
`LabelEncoder`	Transformer to encode labels into [0, n_uniques - 1].